Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    mixing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     působ
    -0.07
     características
    -0.06
    .HandlerFunc
    -0.06
     sommes
    -0.06
     disrupting
    -0.06
     σχέ
    -0.06
    .imp
    -0.06
    oses
    -0.06
    atisch
    -0.06
     оди
    -0.06
    POSITIVE LOGITS
     Mixing
    0.07
     関
    0.06
     كبيرة
    0.06
    時
    0.06
    	glfw
    0.06
    ürnberg
    0.06
    dq
    0.06
    Except
    0.06
    omite
    0.06
     frying
    0.06
    Act Density 0.001%

    No Known Activations